Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking

Kleeberger, Kilian; Landgraf, Christian; Huber, Marco F.

doi:10.48550/arxiv.1912.12125

Cited by 4 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object detection and 6D pose estimation play an important role in many technological areas. With the increasing availability of RGB-D cameras, numerous datasets has appeared [2], [14], [15], [4], [16], [17], [9]. A summary of all these datasets is presented in [17], and in the benchmark for 6D object pose estimation (BOP) [11], the authors have performed a comprehensive evaluation of 15 diverse approaches on eight recent datasets.…”

Section: A Datasets For Object Detection and 6d Pose Estimationmentioning

confidence: 99%

“…The same scene was recorded from different viewpoints for evaluating object pose estimation and active vision techniques. Recently, the Fraunhofer IPA dataset [17] has been introduced for object pose estimation and instance segmentation for robotic bin-picking. However, it contains only 520 real-world depth images of two industrial objects.…”

Section: A Datasets For Object Detection and 6d Pose Estimationmentioning

confidence: 99%

See 1 more Smart Citation

ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking

Yang¹,

Gao²,

Liu³

et al. 2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

In robotic bin-picking applications, the perception of texture-less, highly reflective parts is a valuable but challenging task. The high glossiness can introduce fake edges in RGB images and inaccurate depth measurements especially in heavily cluttered bin scenario. In this paper, we present the ROBI (Reflective Objects in BIns) dataset, a public dataset for 6D object pose estimation and multi-view depth fusion in robotic bin-picking scenarios. The ROBI dataset includes a total of 63 bin-picking scenes captured with two active stereo camera: a high-cost Ensenso sensor and a low-cost RealSense sensor. For each scene, the monochrome/RGB images and depth maps are captured from sampled view spheres around the scene, and are annotated with accurate 6D poses of visible objects and an associated visibility score. For evaluating the performance of depth fusion, we captured the ground truth depth maps by high-cost Ensenso camera with objects coated in anti-reflective scanning spray. To show the utility of the dataset, we evaluated the representative algorithms of 6D object pose estimation and multi-view depth fusion on the full dataset. Evaluation results demonstrate the difficulty of highly reflective objects, especially in difficult cases due to the degradation of depth data quality, severe occlusions and cluttered scene. The ROBI dataset is available online at https://www.trailab.utias.utoronto.ca/robi.

show abstract

Section: A Datasets For Object Detection and 6d Pose Estimationmentioning

confidence: 99%

Section: A Datasets For Object Detection and 6d Pose Estimationmentioning

confidence: 99%

ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking

Yang¹,

Gao²,

Liu³

et al. 2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…We have trained both OP-Net [2] and Multistream ValidNet on 8 objects from the Fraunhofer IPA dataset [18]. We then tested using these same 8 objects as collected in the Siléane ideal dataset [19], which is similar to the training and testing protocol followed by OP-Net.…”

Section: Datasetmentioning

confidence: 99%

Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation

Mazumder¹,

Zand²,

Greenspan³

2021

Preprint

View full text Add to dashboard Cite

This work presents a novel approach to improve the results of pose estimation by detecting and distinguishing between the occurrence of True and False Positive results. It achieves this by training a binary classifier on the output of an arbitrary pose estimation algorithm, and returns a binary label indicating the validity of the result. We demonstrate that our approach improves upon a state-of-the-art pose estimation result on the Siléane dataset, outperforming a variation of the alternative CullNet method by 4.15% in average class accuracy and 0.73% in overall accuracy at validation. Applying our method can also improve the pose estimation average precision results of Op-Net by 6.06% on average.

show abstract

“…Note σ p is computed perframe for updating Equations ( 11) - (15). To fully take advantage of estimated uncertainties, a per-frame inlier probability π k is computed for F k in [10], to replace the expectation of Beta(π|a k−1 , b k−1 ) in Equation ( 11) and (12). Inspired by this, we employ the estimated photometric uncertainty C for evaluating inlier probability π k .…”

Section: Probabilistic Volumetric Integrationmentioning

confidence: 99%

“…To demonstrate the advantages of our framework, we present a real-world dataset in bin-picking scenarios. Compared to existing bin-picking related datasets [1], [3], [11], [12], our dataset has unique characteristics. It consists of reflective parts and over 30 individual bin instances.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Multi-View Fusion of Active Stereo Depth Maps for Robotic Bin-Picking

Yang

Waslander

2021

Preprint

View full text Add to dashboard Cite

The reliable fusion of depth maps from multiple viewpoints has become an important problem in many 3D reconstruction pipelines. In this work, we investigate its impact on robotic bin-picking tasks such as 6D object pose estimation. The performance of object pose estimation relies heavily on the quality of depth data. However, due to the prevalence of shiny surfaces and cluttered scenes, industrial grade depth cameras often fail to sense depth or generate unreliable measurements from a single viewpoint. To this end, we propose a novel probabilistic framework for scene reconstruction in robotic binpicking. Based on active stereo camera data, we first explicitly estimate the uncertainty of depth measurements for mitigating the adverse effects of both noise and outliers. The uncertainty estimates are then incorporated into a probabilistic model for incrementally updating the scene. To extensively evaluate the traditional fusion approach alongside our own approach, we will release a novel representative dataset with multiple views for each bin and curated parts. Over the entire dataset, we demonstrate that our framework outperforms a traditional fusion approach by a 12.8% reduction in reconstruction error, and 6.1% improvement in detection rate. The dataset will be available at https://www.trailab.utias.utoronto.ca/robi.

show abstract

Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking

Cited by 4 publications

References 0 publications

ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking

ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking

Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation

Probabilistic Multi-View Fusion of Active Stereo Depth Maps for Robotic Bin-Picking

Contact Info

Product

Resources

About